Ambulance crews play an important role in responding quickly to emergencies and rescuing patients by providing appropriate treatment. Typically, fully equipped emergency vehicles are used to transport ambulance personnel to emergency locations. The ambulance crew cleans, sterilizes, and prepares equipment after each patient transfer with great care. Additionally, they check more than 70 pieces of equipment twice a day using a checklist, which is a tedious, time-consuming, and error-prone task. This study uses computer vision and deep learning techniques to replace the manual checklist process for medical equipment to assist the crew and make the equipment availability check faster and easier. To accomplish this, a dataset containing 2099 images of medical equipment in ambulances was collected and annotated with 3000 labeled instances. An experimental study compared the performance of YOLOv9-c, YOLOv8n, and YOLOv7-tiny. YOLOv8n demonstrated the best performance with a mAP50 of 99.2% and a speed of 3.3 ms total time per image. Therefore, YOLOv8 was selected for the proposed system due to its high accuracy and detection speed, which make it suitable for mobile applications. The presence of an application integrated with computer vision and deep learning technologies in paramedic devices can assist in reviewing the equipment checklist, reducing human errors, speeding up the review process, and alleviating the burden on paramedics in their work.